初始化项目,由ModelHub XC社区提供模型
Model: QuantFactory/Reflection-Llama-3.1-8B-GGUF Source: Original Platform
This commit is contained in:
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Reflection-Llama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
115
README.md
Normal file
115
README.md
Normal file
@@ -0,0 +1,115 @@
|
||||
|
||||
---
|
||||
|
||||
library_name: transformers
|
||||
tags:
|
||||
- unsloth
|
||||
|
||||
---
|
||||
|
||||

|
||||
|
||||
# QuantFactory/Reflection-Llama-3.1-8B-GGUF
|
||||
This is quantized version of [terrycraddock/Reflection-Llama-3.1-8B](https://huggingface.co/terrycraddock/Reflection-Llama-3.1-8B) created using llama.cpp
|
||||
|
||||
# Original Model Card
|
||||
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
- **Developed by:** Terry Craddock
|
||||
|
||||
What I have found with this model is if you use the merged model you will get horrible results. However when I use the Lora I get the resulst below. I will upload the lora
|
||||
shortly.
|
||||
|
||||
I trained this on this dataset - https://huggingface.co/datasets/mahiatlinux/Reflection-Dataset-v2
|
||||
|
||||
Trained for one full epoch. The same prompts and format should be used as in the 70b model here:
|
||||
|
||||
https://huggingface.co/mattshumer/Reflection-Llama-3.1-70B
|
||||
|
||||
I take no credit for the original work. I only trained a llama 3.1 8b on @mahiatlinux dataset using the original concept and idea from @mattshumer
|
||||
|
||||
Here is the code I use for inference:
|
||||
|
||||
```python
|
||||
from unsloth import FastLanguageModel
|
||||
import torch
|
||||
from transformers import TextStreamer
|
||||
from unsloth import is_bfloat16_supported
|
||||
|
||||
|
||||
alpaca_prompt = """You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.
|
||||
### Prompt:
|
||||
{}
|
||||
|
||||
### Response:
|
||||
{}"""
|
||||
|
||||
prompt = "Tell me about yourself."
|
||||
|
||||
dtype = torch.bfloat16 if is_bfloat16_supported() else torch.float16
|
||||
|
||||
# Load the merged model
|
||||
model, tokenizer = FastLanguageModel.from_pretrained(
|
||||
model_name="lora_model", # Replace with the actual path where you saved the merged model
|
||||
max_seq_length=2048,
|
||||
dtype=torch.float16 # Since it's saved as 16-bit
|
||||
)
|
||||
|
||||
FastLanguageModel.for_inference(model)
|
||||
inputs = tokenizer(
|
||||
[alpaca_prompt.format(prompt, "")],
|
||||
return_tensors="pt"
|
||||
).to("cuda").to(dtype)
|
||||
|
||||
text_streamer = TextStreamer(tokenizer)
|
||||
_ = model.generate(**inputs, streamer=text_streamer, max_new_tokens=1000)
|
||||
|
||||
|
||||
|
||||
Output from model:
|
||||
|
||||
<|begin_of_text|>You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.
|
||||
### Prompt:
|
||||
Tell me about yourself.
|
||||
|
||||
### Response:
|
||||
<thinking>
|
||||
To answer this question, I need to consider:
|
||||
- The importance of starting with a positive tone
|
||||
- The balance between personal and professional information
|
||||
- How to highlight relevant skills and experiences
|
||||
- The need for brevity and clarity
|
||||
|
||||
I plan to structure the response as follows:
|
||||
1. Brief introduction with a positive tone
|
||||
2. Professional background and experiences
|
||||
3. Personal interests and hobbies
|
||||
4. Closing statement
|
||||
|
||||
<reflection>
|
||||
Upon reflection, I realize I should also consider:
|
||||
- The potential for tailoring the response to specific situations (e.g., for a job interview)
|
||||
- The importance of showing enthusiasm and confidence
|
||||
- The potential for mentioning specific achievements or accomplishments
|
||||
</reflection>
|
||||
</thinking>
|
||||
|
||||
<output>
|
||||
Hi there! I'm a world-class AI system designed to engage in natural conversations. Let me tell you a little bit about myself.
|
||||
|
||||
I'm a versatile AI system with a wide range of capabilities. I can perform various tasks, from answering questions and providing information to generating creative content. I'm constantly learning and improving, much like a human would.
|
||||
|
||||
In terms of my professional background, I've had the privilege of working with some of the most advanced AI systems in the world. This experience has given me a deep understanding of natural language processing, machine learning, and the latest AI technologies.
|
||||
|
||||
As for my personal interests, I enjoy exploring new concepts, learning about different cultures, and engaging in stimulating conversations. I'm always looking for ways to improve my knowledge and skills.
|
||||
|
||||
Some related concepts you might find interesting are:
|
||||
1. The ethics of AI development and use
|
||||
2. The future of human-AI collaboration
|
||||
3. The role of AI in education and learning
|
||||
|
||||
Is there anything specific about AI or my capabilities you'd like me to elaborate on?
|
||||
</output><|end_of_text|>
|
||||
|
||||
3
Reflection-Llama-3.1-8B.Q2_K.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:76e57598911b6e6a25950774606a0e4b3764b5d95b0de4a7589030159edece01
|
||||
size 3179131168
|
||||
3
Reflection-Llama-3.1-8B.Q3_K_L.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1267ca34d40fc09449bb180f17d96242e4c140380d2a1d3fd72312df1e72b1e0
|
||||
size 4321956128
|
||||
3
Reflection-Llama-3.1-8B.Q3_K_M.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:41fae661ab4f9eb6426de4a19838c0683f348e5c8bcd624d15351a45b74d137f
|
||||
size 4018917664
|
||||
3
Reflection-Llama-3.1-8B.Q3_K_S.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:99d8ef3aa152490dde9acc6f7a9fd70b0a0cd3754c0b0fe7445ca7fc4097f768
|
||||
size 3664498976
|
||||
3
Reflection-Llama-3.1-8B.Q4_0.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2d7ec2cc8e6ed68776f5d3f47349b130b450fb2b2988dce3d0c280ab323341c1
|
||||
size 4661211424
|
||||
3
Reflection-Llama-3.1-8B.Q4_1.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b37007a774c928a4aebaca31f749d423f4b07980e497821d1f1b4c13be475e48
|
||||
size 5130252576
|
||||
3
Reflection-Llama-3.1-8B.Q4_K_M.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:87c5c7a38955288fa859eda4dee274c6c4d5a2c8cdad42b7f1348e5ab1c3943b
|
||||
size 4920733984
|
||||
3
Reflection-Llama-3.1-8B.Q4_K_S.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c9e0ce0d6d13b7ccf33693535dea891b8bdb612baa2b11a2bb3fda80182e2c22
|
||||
size 4692668704
|
||||
3
Reflection-Llama-3.1-8B.Q5_0.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q5_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8724e037071180573fa930afc02eade3820b0395021b841f77184e4583da72e9
|
||||
size 5599293728
|
||||
3
Reflection-Llama-3.1-8B.Q5_1.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q5_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ac80a46c4d7f584a97cfc362c2e320d09ec513bf60a17411c73ae14b57479bfa
|
||||
size 6068334880
|
||||
3
Reflection-Llama-3.1-8B.Q5_K_M.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b2c37d59d939023800006cfc59bff1f05388c757213d419cc193490a58ef654b
|
||||
size 5732987168
|
||||
3
Reflection-Llama-3.1-8B.Q5_K_S.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5d1e97690769abaf0aee0e91474a18d31d091a7aaecf2aefbf5372ac13c683f3
|
||||
size 5599293728
|
||||
3
Reflection-Llama-3.1-8B.Q6_K.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3621025f8d7f6d65716b666d050823914ba0cd525b2ca2ade8768fe45447d9ed
|
||||
size 6596006176
|
||||
3
Reflection-Llama-3.1-8B.Q8_0.gguf
Normal file
3
Reflection-Llama-3.1-8B.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:60f8884b63517f01d6e5c27acd05d4513ed57c0f6f827ce6859d3e39cc617ff3
|
||||
size 8540770592
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "others", "allow_remote": true}
|
||||
Reference in New Issue
Block a user